D3rlpy: An Offline Deep Reinforcement Learning Library

Abstract

In this paper, we introduce d3rlpy, an open-sourced offline deep reinforcement learning (RL) library for Python. d3rlpy supports a set of offline deep RL algorithms as well as off-policy online algorithms via a fully documented plug-and-play API. To address a reproducibility issue, we conduct a large-scale benchmark with D4RL and Atari 2600 dataset to ensure implementation quality and provide experimental scripts and full tables of results. The d3rlpy source code can be found on GitHub: https://github.com/takuseno/d3rlpy.

Cite

Text

Seno and Imai. "D3rlpy: An Offline Deep Reinforcement Learning Library." Machine Learning Open Source Software, 2022.

Markdown

[Seno and Imai. "D3rlpy: An Offline Deep Reinforcement Learning Library." Machine Learning Open Source Software, 2022.](https://mlanthology.org/mloss/2022/seno2022jmlr-d3rlpy/)

BibTeX

@article{seno2022jmlr-d3rlpy,
  title     = {{D3rlpy: An Offline Deep Reinforcement Learning Library}},
  author    = {Seno, Takuma and Imai, Michita},
  journal   = {Machine Learning Open Source Software},
  year      = {2022},
  pages     = {1-20},
  volume    = {23},
  url       = {https://mlanthology.org/mloss/2022/seno2022jmlr-d3rlpy/}
}